• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 봄 학술논문 발표대회
• /
• pp.73-74
• /
• 2022

Concrete structures occupy the largest proportion of modern infrastructure, and concrete structures often have cracking problems. Existing concrete crack diagnosis methods have limitations in crack evaluation because they rely on expert visual inspection. Therefore, in this study, we design a deep learning model that detects, visualizes, and outputs cracks on the surface of RC structures based on image data by using a CNN (Convolution Neural Networks) model that can process two- and three-dimensional data such as video and image data. do. An experimental study was conducted on an algorithm to automatically detect concrete cracks and visualize them using a CNN model. For the three deep learning models used for algorithm learning in this study, the concrete crack prediction accuracy satisfies 90%, and in particular, the 'InceptionV3'-based CNN model showed the highest accuracy. In the case of the crack detection visualization model, it showed high crack detection prediction accuracy of more than 95% on average for data with crack width of 0.2 mm or more.

• 전자통신동향분석
• /
• 제39권2호
• /
• pp.24-32
• /
• 2024

Wearable metaverse devices have sparked enthusiasm as innovative virtual computing user interfaces by addressing a major source of user discomfort, namely, motion-to-photon latency. This kind of latency occurs between the user motion and screen update. To enhance the realism and immersion of experiences using metaverse devices, the vergence-accommodation conflict in stereoscopic image representation must be resolved. Ongoing research aims to address current challenges by adopting vari-focal, multifocal, and light field display technologies for stereoscopic imaging. We explore current trends in research with emphasis on multifocal stereoscopic imaging. Successful metaverse visualization services require the integration of stereoscopic image rendering modules and content encoding/decoding technologies tailored to these services. Additionally, real-time video processing is essential for these modules to correctly and timely process such content and implement metaverse visualization services.

• 한국가시화정보학회지
• /
• 제14권2호
• /
• pp.18-24
• /
• 2016

This paper presents an experimental investigation to visualize cross-sectional two-phase flow structure and identify liquid-gas interface for condensation of steam at a low mass flux in a slightly inclined tube using the axial-viewing technique, which permits to look directly into flow during condensation of steam. In this technique, two-phase flow is viewed along the axis of a pipe by locating a high-speed video camera in front of a viewer that is fitted at the outlet of the pipe. A short section of the pipe is illuminated and is recorded through the viewer, which is kept free of liquid by mildly introducing air. Experiments were conducted in a pipe of 19.05 mm in inner diameter at atmospheric pressure. Cross-sectional two-phase flow structure is obtained at a steam mass flux of $2.62kg/m^2s$ as a function of steam quality in the range from 0.5 to 0.9. The results show that stratified-wavy flow is a unique flow pattern observed in the scope of the present study. Condensate film thickness, stratification angle and void fraction were measured from the obtained flow structure images. Finally, heat transfer coefficient was calculated using the measurement data and discussed in comparison with existing correlations.

• 대한기계학회논문집B
• /
• 제25권12호
• /
• pp.1684-1691
• /
• 2001

Electrorheological fluids(ERFs) show a rapid and reversible increase in apparent viscosity by applied electric field. It is called the electrorheological effect (ER effect). The reason for ER effect is the induction of an electric dipole in each particle, leading to the formation of clusters in the direction of the field, which resist fluid flow. Generally, the behavior of ER fluids has been modeled on those of Bingham fluids. But there are some differences between Bingham fluids and ER fluids. The visualization of ER fliuds are presented and ER effects by the forming, growing and breaking of clusters are discussed. In the low shear rate area, the pressure drop is measured by a pressure sensor and the formation of ER particles is visualized by video camera. The reason for the nonlinear behavior of ER fluids at low shear rate is explained through results of visualization. As result, the behavior of ER fluids is nonlinear at low shear rate with overshoot area because it is different to from the clusters according to the strength of electric field. The gap of electrodes becomes narrow because of the cluster layer occurrence near to electrodes in any conditions.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 1999년도 추계종합학술대회
• /
• pp.420-423
• /
• 1999

본 논문에서는 비디오를 사용자가 쉽고 빠른 편집과 검색을 통하여 효율적으로 정보를 습득 할 수 있는 방법을 제안한다. 본 논문에서 제안하는 방법은 기존의 장면변환 검출 기법을 통해 추출된 후보 대표프레임들 중에서 사용자의 판단에 의해 대표프레임을 설정, 장면을 분할한 뒤 사용자 편의를 위해 시각적인 색인화를 통해 사용-자가 임의대로 각각의 장면들을 논리적으로 병합, 분리 가능하게 하여 편집할 수 있도록 한다.

• 한국공간정보시스템학회 논문지
• /
• 제11권2호
• /
• pp.45-53
• /
• 2009

The fast progress on multimedia data acquisition technologies has enabled collecting vast amount of videos in real time. Although the amount of information gathered from these videos could be high in terms of quantity and quality, the use of the collected data is very limited typically by human-centric monitoring systems. In this paper, we propose a framework for analyzing long traffic video using series of content-based analyses tools. Our framework suggests a method to integrate theses analyses tools to extract highly informative features specific to a traffic video analysis. Our analytical framework provides (1) re-sampling tools for efficient and precise analysis, (2) foreground extraction methods for unbiased traffic flow analysis, (3) frame property analyses tools using variety of frame characteristics including brightness, entropy, Harris corners, and variance of traffic flow, and (4) a visualization tool that summarizes the entire video sequence and automatically highlight a collection of frames based on some metrics defined by semi-automated or fully automated techniques. Based on the proposed framework, we developed an automated traffic flow analysis system, and in our experiments, we show results from two example traffic videos taken from different monitoring angles.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권9호
• /
• pp.1150-1160
• /
• 2004

본 논문에서는 MPEG-2에서 정의한 시공간적 계위를 확장하여 enhanced Access Grid (e-AG) 상의 서로 다른 디스플레이 시스템 및 네트워크 환경을 가진 수신 단말의 효율적인 디스플레이를 위한 새로운 3차원 영상의 부호화 방법을 제안한다. 제안된 부호화기는 3차원 영상에 대해서 시공간적 기본 해상도 및 고 해상도의 영상을 표현 가능하도록 여러 계층의 비트 열을 생성한다. 생성된 비트 열은 수신 단말의 네트워크 환경 및 처리속도, 디스플레이 환경에 따라 다른 시공간적 해상포론 표현할 수 있도록 선택적으로 전송된다. 제안된 시공간적 계위를 이용한 3차원 영상 부호화기는 이질적인 분산환경에서의 효율적인 3차원 비디오 전송 서비스에 활용 가능하다.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1997년도 추계학술대회
• /
• pp.137-141
• /
• 1997

In this study, in order to improve visualization and enhance the ability of the surgeon to perform delicate endoscopic surgery, three dimensional endoscopic system is designed. These 3D systems have our features of stereoendoscopic image processing: real time image capture and retrieve; presentation of left and right image on a single monitor; separable processing of the left and right eye images; coding of the 3D endoscopic video. For 3D endoscopic video coding, three approaches are presented based on interlaced picture structure, side-field format structure, and simulcast technique. Experimental results and performances comparisons are presented and analyzed or these approaches. Digital video coding techniques are presented or 3D endoscopic video sequences by means of an MPEG-2 video coding.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2002년도 추계학술발표논문집 (하)
• /
• pp.1903-1906
• /
• 2002

비디오 GIS 는 비디오 데이터가 지도 또는 3 차원 그래픽스, 이미지, 비디오, 위성영상 등의 여러 가지 매체와 통합 연계되어 사용되고 관리되는 시스템이다. 특히 비디오 형태의 정보는 그 특성상 지리정보의 사실적인 정보를 제공해 줄 수 있으므로, 공간객체의 실제 모습을 촬영하여 지도 데이터와 연계함으로써 현실적이고 사실적인 시각화를 더하여 기존 지도 중심의 GIS 의 단점을 보완할 수 있다. 비디오 GIS 에서는 비디오 데이터에 위치정보를 포함함으로써 비디오가 지리정보와 연계되어 양방향 검색과 브라우징, 분석 등을 제공해 줄 수 있다. 본 논문에서는 비디오와 지도 정보를 통합하여 관리하고 공간정보를 구축할 수 있는 비디오 GIS 기술 및 공간데이터를 구축하는 방법을 제시하며 프로토타입 시스템 개발 결과 및 도로시설물 관리 분야에 적용한 결과를 제시한다.

• 멤브레인
• /
• 제13권3호
• /
• pp.174-181
• /
• 2003

본 실험에서는 십자형 흐름 정밀여과 모듈에서 분리막 투과시 막표면에 일어나는 입자층의 형성을 고속비디오 시스템으로 관찰하였다. 공칭세공이 0.2 {\mu}m$ 정밀여과막과 기공크기보다 휠씬 큰 100 내지 180{\mu}m$ 크기의 polyacryl-copolymer 0.05 wt%의 농도 용액을 제조하여 투과실험에서는 공급유속을 0.5, 0.75, 1.0, 1.25 그리고 1.5 cm/sec으로 변화시키면서 공급유속의 $20{\pm}3%$로 투과유량을 유지하였다. 공급유량이 증가할수록 입자가 보다 신속히 분리막 표면에 축적되는 것을 관찰할 수 있었고 공급유량이 낮은 0.5 cm/sec 에서는 입자층이 형성되지 않았다. 또한 입자층 형성 후 공급 유속을 1.88 cm/sec로 증가시키면 30초이내에 분리막 표면에 입자들이 대부분 제거됨을 확인하였다.